Photo Credit: bumathew

The following is a summary of “Artificial intelligence networks for assessing the prognosis of gastrointestinal cancer to immunotherapy based on genetic mutation features: a systematic review and meta-analysis,” published in the April 2025 issue of BMC Gastroenterology by Norouzkhani et al. 

Artificial intelligence (AI) networks demonstrated significant potential for predicting immunotherapy outcomes in gastrointestinal cancers by analyzing genetic mutation profiles, though their application in prognosis had remained underexplored.  

Researchers conducted a retrospective study to assess the effectiveness of AI-based models in predicting immunotherapy responses in gastrointestinal cancers using genetic mutation features.  

They followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to evaluate AI networks for predicting gastrointestinal cancer prognosis in response to immunotherapy using genetic mutation features. A search in PubMed, Web of Science (WOS), and Scopus identified relevant studies. Data extraction and quality assessment were completed, and statistical analysis included pooled estimates for sensitivity, specificity, accuracy, and area under the curve (AUC). Regression models and imputation methods addressed missing values to ensure robust results, and the data were analyzed using STATA version 18.  

The results showed that 45 studies published in 2024 involving 14,047 participants in training sets and 10,885 participants in test sets were included. The pooled performance of AI models for gastrointestinal cancers based on genetic mutation features was: AUC = 0.86 (95% CI: 0.86–0.87), sensitivity = 83% (95% CI: 83%-84%), specificity = 72% (95% CI: 72%-73%), and accuracy = 82% (95% CI: 82%-83%). Heterogeneity was low to moderate, and no publication bias was detected. Subgroup analysis revealed a higher AUC for gastric cancer models (AUC: 0.87) and a lower AUC for pancreatic cancer models (AUC: 0.52).  

Investigators concluded that AI networks showed significant promise in predicting immunotherapy outcomes for gastrointestinal cancers using genetic mutation features, effectively stratifying patients, and aiding treatment optimization. 

Source: bmcgastroenterol.biomedcentral.com/articles/10.1186/s12876-025-03884-1